Put the ipynb file and html file in the github branch you created in the last assignment and submit the link to the commit in brightspace
from plotly.offline import init_notebook_mode
import plotly.io as pio
import plotly.express as px
import pandas as pd
init_notebook_mode(connected=True)
pio.renderers.default = "plotly_mimetype+notebook"
#load data
df = px.data.gapminder()
df.head()
| country | continent | year | lifeExp | pop | gdpPercap | iso_alpha | iso_num | |
|---|---|---|---|---|---|---|---|---|
| 0 | Afghanistan | Asia | 1952 | 28.801 | 8425333 | 779.445314 | AFG | 4 |
| 1 | Afghanistan | Asia | 1957 | 30.332 | 9240934 | 820.853030 | AFG | 4 |
| 2 | Afghanistan | Asia | 1962 | 31.997 | 10267083 | 853.100710 | AFG | 4 |
| 3 | Afghanistan | Asia | 1967 | 34.020 | 11537966 | 836.197138 | AFG | 4 |
| 4 | Afghanistan | Asia | 1972 | 36.088 | 13079460 | 739.981106 | AFG | 4 |
Recreate the barplot below that shows the population of different continents for the year 2007.
Hints:
df_2007 = df.query('year==2007')
df_2007_new = df_2007.groupby('continent').sum()
fig = px.bar(df_2007_new, x="pop", orientation='h', color = df_2007_new.index, text_auto='.3s')
fig.show()
fig = px.bar(df_2007_new, x="pop", orientation='h', color = df_2007_new.index)
fig.update_layout(yaxis={'categoryorder':'total ascending'})
fig.show()
Add text to each bar that represents the population
fig = px.bar(df_2007_new, x="pop", orientation='h', color = df_2007_new.index, text_auto='.3s')
fig.update_layout(yaxis={'categoryorder':'total ascending'})
fig.show()
Thus far we looked at data from one year (2007). Lets create an animation to see the population growth of the continents through the years
fig = px.bar(df, y="continent", x="pop", color="continent",
animation_frame="year", animation_group="country", range_x=[0,4000000000])
fig.show()
Instead of the continents, lets look at individual countries. Create an animation that shows the population growth of the countries through the years
df['country'].unique().__len__() #amount of countries, 142 countries
len(df) #length of dataframe, 1704 rows
1704/142 #amount of years of data per country, 12 years
keys = [i for i in range(142)]
all_dataframes = {}
for i, country in zip(keys, df['country'].unique()):
df2 = df[df['country'] == country].sort_values('year', ascending=True)
all_dataframes[i] = df2
master_df = []
for i in all_dataframes:
master_df.append(all_dataframes[i])
df_all = pd.concat(master_df)
df_all
fig = px.bar(df_all, x='pop', y="country", color='country',
animation_frame="year", animation_group="country")
fig.update_layout(yaxis={'categoryorder':'total ascending'})
fig.show()
Clean up the country animation. Set the height size of the figure to 1000 to have a better view of the animation
df['country'].unique().__len__() #amount of countries, 142 countries
len(df) #length of dataframe, 1704 rows
1704/142 #amount of years of data per country, 12 years
keys = [i for i in range(142)]
all_dataframes = {}
for i, country in zip(keys, df['country'].unique()):
df2 = df[df['country'] == country].sort_values('year', ascending=True)
all_dataframes[i] = df2
master_df = []
for i in all_dataframes:
master_df.append(all_dataframes[i])
df_all = pd.concat(master_df)
df_all
fig = px.bar(df_all, x='pop', y="country", color='country',
animation_frame="year", animation_group="country", height=1000)
fig.update_layout(yaxis={'categoryorder':'total ascending'})
fig.show()
fig.update_yaxes(range=(131.5, 142.5))